[NVPTX] Add __CUDA_ARCH__ macro to standalone NVPTX compilations

We can now target the NVPTX architecture directly via
`--target=nvptx64-nvidia-cuda`. This currently does not define the
`__CUDA_ARCH__` macro with is used to allow code to target different
codes based on support. This patch simply adds this support.

Reviewed By: tra, jdoerfert

Differential Revision: https://reviews.llvm.org/D146975

Author: jhuber6

clang/lib/Basic/Targets/NVPTX.cpp

@@ -168,7 +168,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
                                        MacroBuilder &Builder) const {
   Builder.defineMacro("__PTX__");
   Builder.defineMacro("__NVPTX__");
-  if (Opts.CUDAIsDevice || Opts.OpenMPIsDevice) {
+  if (Opts.CUDAIsDevice || Opts.OpenMPIsDevice || !HostTarget) {
     // Set __CUDA_ARCH__ for the GPU specified.
     std::string CUDAArchCode = [this] {
       switch (GPU) {

clang/test/Frontend/standalone-nvptx-macros.c

@@ -0,0 +1,5 @@
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang %s -c -E -dM --target=nvptx64-nvidia-cuda -march=sm_70 -o - | \
+// RUN:   FileCheck --check-prefix=CHECK-CUDA-ARCH %s
+// CHECK-CUDA-ARCH: #define __CUDA_ARCH__ 700